selftests/bpf: Add usdt trigger bench

Adding usdt trigger bench for usdt:
 trig-usdt-nop  - usdt on top of nop1 instruction
 trig-usdt-nop5 - usdt on top of nop1/nop5 combo

Adding it to benchs/run_bench_uprobes.sh script.

Example run on x86_64 kernel with uprobe syscall:

  # ./benchs/run_bench_uprobes.sh
  usermode-count :  152.507 ± 0.098M/s
  syscall-count  :   14.309 ± 0.093M/s
  uprobe-nop     :    3.190 ± 0.012M/s
  uprobe-push    :    3.057 ± 0.004M/s
  uprobe-ret     :    1.095 ± 0.009M/s
  uprobe-nop5    :    7.305 ± 0.034M/s
  uretprobe-nop  :    2.175 ± 0.005M/s
  uretprobe-push :    2.109 ± 0.003M/s
  uretprobe-ret  :    0.945 ± 0.002M/s
  uretprobe-nop5 :    3.530 ± 0.006M/s
  usdt-nop       :    3.235 ± 0.008M/s   <-- added
  usdt-nop5      :    7.511 ± 0.045M/s   <-- added

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/r/20260224103915.1369690-6-jolsa@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

tools/testing/selftests/bpf/Makefile

@@ -879,6 +879,8 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o \
 		 $(OUTPUT)/bench_bpf_crypto.o \
 		 $(OUTPUT)/bench_sockmap.o \
 		 $(OUTPUT)/bench_lpm_trie_map.o \
+		 $(OUTPUT)/usdt_1.o \
+		 $(OUTPUT)/usdt_2.o \
 		 #
 	$(call msg,BINARY,,$@)
 	$(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@

tools/testing/selftests/bpf/bench.c

@@ -541,6 +541,8 @@ extern const struct bench bench_trig_uprobe_nop5;
 extern const struct bench bench_trig_uretprobe_nop5;
 extern const struct bench bench_trig_uprobe_multi_nop5;
 extern const struct bench bench_trig_uretprobe_multi_nop5;
+extern const struct bench bench_trig_usdt_nop;
+extern const struct bench bench_trig_usdt_nop5;
 #endif
 
 extern const struct bench bench_rb_libbpf;
@@ -617,6 +619,8 @@ static const struct bench *benchs[] = {
 	&bench_trig_uretprobe_nop5,
 	&bench_trig_uprobe_multi_nop5,
 	&bench_trig_uretprobe_multi_nop5,
+	&bench_trig_usdt_nop,
+	&bench_trig_usdt_nop5,
 #endif
 	/* ringbuf/perfbuf benchmarks */
 	&bench_rb_libbpf,

tools/testing/selftests/bpf/benchs/bench_trigger.c

@@ -407,6 +407,23 @@ static void *uprobe_producer_nop5(void *input)
 		uprobe_target_nop5();
 	return NULL;
 }
+
+void usdt_1(void);
+void usdt_2(void);
+
+static void *uprobe_producer_usdt_nop(void *input)
+{
+	while (true)
+		usdt_1();
+	return NULL;
+}
+
+static void *uprobe_producer_usdt_nop5(void *input)
+{
+	while (true)
+		usdt_2();
+	return NULL;
+}
 #endif
 
 static void usetup(bool use_retprobe, bool use_multi, void *target_addr)
@@ -544,6 +561,47 @@ static void uretprobe_multi_nop5_setup(void)
 {
 	usetup(true, true /* use_multi */, &uprobe_target_nop5);
 }
+
+static void usdt_setup(const char *name)
+{
+	struct bpf_link *link;
+	int err;
+
+	setup_libbpf();
+
+	ctx.skel = trigger_bench__open();
+	if (!ctx.skel) {
+		fprintf(stderr, "failed to open skeleton\n");
+		exit(1);
+	}
+
+	bpf_program__set_autoload(ctx.skel->progs.bench_trigger_usdt, true);
+
+	err = trigger_bench__load(ctx.skel);
+	if (err) {
+		fprintf(stderr, "failed to load skeleton\n");
+		exit(1);
+	}
+
+	link = bpf_program__attach_usdt(ctx.skel->progs.bench_trigger_usdt,
+					0 /*self*/, "/proc/self/exe",
+					"optimized_attach", name, NULL);
+	if (libbpf_get_error(link)) {
+		fprintf(stderr, "failed to attach optimized_attach:%s usdt probe\n", name);
+		exit(1);
+	}
+	ctx.skel->links.bench_trigger_usdt = link;
+}
+
+static void usdt_nop_setup(void)
+{
+	usdt_setup("usdt_1");
+}
+
+static void usdt_nop5_setup(void)
+{
+	usdt_setup("usdt_2");
+}
 #endif
 
 const struct bench bench_trig_syscall_count = {
@@ -611,4 +669,6 @@ BENCH_TRIG_USERMODE(uprobe_nop5, nop5, "uprobe-nop5");
 BENCH_TRIG_USERMODE(uretprobe_nop5, nop5, "uretprobe-nop5");
 BENCH_TRIG_USERMODE(uprobe_multi_nop5, nop5, "uprobe-multi-nop5");
 BENCH_TRIG_USERMODE(uretprobe_multi_nop5, nop5, "uretprobe-multi-nop5");
+BENCH_TRIG_USERMODE(usdt_nop, usdt_nop, "usdt-nop");
+BENCH_TRIG_USERMODE(usdt_nop5, usdt_nop5, "usdt-nop5");
 #endif

tools/testing/selftests/bpf/benchs/run_bench_uprobes.sh

@@ -2,7 +2,7 @@
 
 set -eufo pipefail
 
-for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5}
+for i in usermode-count syscall-count {uprobe,uretprobe}-{nop,push,ret,nop5} usdt-nop usdt-nop5
 do
 	summary=$(sudo ./bench -w2 -d5 -a trig-$i | tail -n1 | cut -d'(' -f1 | cut -d' ' -f3-)
 	printf "%-15s: %s\n" $i "$summary"

tools/testing/selftests/bpf/progs/trigger_bench.c

@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2020 Facebook
-#include <linux/bpf.h>
+#include "vmlinux.h"
 #include <asm/unistd.h>
 #include <bpf/bpf_helpers.h>
 #include <bpf/bpf_tracing.h>
 #include "bpf_misc.h"
+#include "bpf/usdt.bpf.h"
 
 char _license[] SEC("license") = "GPL";
 
@@ -180,3 +181,10 @@ int bench_trigger_rawtp(void *ctx)
 	handle(ctx);
 	return 0;
 }
+
+SEC("?usdt")
+int bench_trigger_usdt(void *ctx)
+{
+	inc_counter();
+	return 0;
+}